Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    furries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Affordable
    -0.07
    (abs
    -0.07
     ఆన
    -0.07
     Amp
    -0.07
     Last
    -0.07
     aliqu
    -0.07
     trocken
    -0.07
    .increment
    -0.07
     precision
    -0.07
    (optional
    -0.07
    POSITIVE LOGITS
     humano
    0.10
    _converter
    0.10
     disguised
    0.09
    -purple
    0.09
     translator
    0.08
     masquer
    0.08
    'an
    0.08
     convertido
    0.08
    -human
    0.08
    Converter
    0.08
    Act Density 0.049%

    No Known Activations